OBJECTIVE: Apply machine learning for the prediction and identification of factors associated with short and long-term mortality in Asian STEMI patients and compare with a conventional risk score.
METHODS: The National Cardiovascular Disease Database for Malaysia registry, of a multi-ethnic, heterogeneous Asian population was used for in-hospital (6299 patients), 30-days (3130 patients), and 1-year (2939 patients) model development. 50 variables were considered. Mortality prediction was analysed using feature selection methods with machine learning algorithms and compared to Thrombolysis in Myocardial Infarction (TIMI) score. Invasive management of varying degrees was selected as important variables that improved mortality prediction.
RESULTS: Model performance using a complete and reduced variable produced an area under the receiver operating characteristic curve (AUC) from 0.73 to 0.90. The best machine learning model for in-hospital, 30 days, and 1-year outperformed TIMI risk score (AUC = 0.88, 95% CI: 0.846-0.910; vs AUC = 0.81, 95% CI:0.772-0.845, AUC = 0.90, 95% CI: 0.870-0.935; vs AUC = 0.80, 95% CI: 0.746-0.838, AUC = 0.84, 95% CI: 0.798-0.872; vs AUC = 0.76, 95% CI: 0.715-0.802, p < 0.0001 for all). TIMI score underestimates patients' risk of mortality. 90% of non-survival patients are classified as high risk (>50%) by machine learning algorithm compared to 10-30% non-survival patients by TIMI. Common predictors identified for short- and long-term mortality were age, heart rate, Killip class, fasting blood glucose, prior primary PCI or pharmaco-invasive therapy and diuretics. The final algorithm was converted into an online tool with a database for continuous data archiving for algorithm validation.
CONCLUSIONS: In a multi-ethnic population, patients with STEMI were better classified using the machine learning method compared to TIMI scoring. Machine learning allows for the identification of distinct factors in individual Asian populations for better mortality prediction. Ongoing continuous testing and validation will allow for better risk stratification and potentially alter management and outcomes in the future.
METHODS: We did a systematic review for studies on anal HPV infection in men and a pooled analysis of individual-level data from eligible studies across four groups: HIV-positive men who have sex with men (MSM), HIV-negative MSM, HIV-positive men who have sex with women (MSW), and HIV-negative MSW. Studies were required to inform on type-specific HPV infection (at least HPV16), detected by use of a PCR-based test from anal swabs, HIV status, sexuality (MSM, including those who have sex with men only or also with women, or MSW), and age. Authors of eligible studies with a sample size of 200 participants or more were invited to share deidentified individual-level data on the above four variables. Authors of studies including 40 or more HIV-positive MSW or 40 or more men from Africa (irrespective of HIV status and sexuality) were also invited to share these data. Pooled estimates of anal high-risk HPV (HR-HPV, including HPV16, 18, 31, 33, 35, 39, 45, 51, 52, 56, 58, 59, and 68), and HSIL or worse (HSIL+), were compared by use of adjusted prevalence ratios (aPRs) from generalised linear models.
FINDINGS: The systematic review identified 93 eligible studies, of which 64 contributed data on 29 900 men to the pooled analysis. Among HIV-negative MSW anal HPV16 prevalence was 1·8% (91 of 5190) and HR-HPV prevalence was 6·9% (345 of 5003); among HIV-positive MSW the prevalences were 8·7% (59 of 682) and 26·9% (179 of 666); among HIV-negative MSM they were 13·7% (1455 of 10 617) and 41·2% (3798 of 9215), and among HIV-positive MSM 28·5% (3819 of 13 411) and 74·3% (8765 of 11 803). In HIV-positive MSM, HPV16 prevalence was 5·6% (two of 36) among those age 15-18 years and 28·8% (141 of 490) among those age 23-24 years (ptrend=0·0091); prevalence was 31·7% (1057 of 3337) among those age 25-34 years and 22·8% (451 of 1979) among those age 55 and older (ptrend<0·0001). HPV16 prevalence in HIV-negative MSM was 6·7% (15 of 223) among those age 15-18 and 13·9% (166 of 1192) among those age 23-24 years (ptrend=0·0076); the prevalence plateaued thereafter (ptrend=0·72). Similar age-specific patterns were observed for HR-HPV. No significant differences for HPV16 or HR-HPV were found by age for either HIV-positive or HIV-negative MSW. HSIL+ detection ranged from 7·5% (12 of 160) to 54·5% (61 of 112) in HIV-positive MSM; after adjustment for heterogeneity, HIV was a significant predictor of HSIL+ (aPR 1·54, 95% CI 1·36-1·73), HPV16-positive HSIL+ (1·66, 1·36-2·03), and HSIL+ in HPV16-positive MSM (1·19, 1·04-1·37). Among HPV16-positive MSM, HSIL+ prevalence increased with age.
INTERPRETATION: High anal HPV prevalence among young HIV-positive and HIV-negative MSM highlights the benefits of gender-neutral HPV vaccination before sexual activity over catch-up vaccination. HIV-positive MSM are a priority for anal cancer screening research and initiatives targeting HPV16-positive HSIL+.
FUNDING: International Agency for Research on Cancer.
METHODS: Studies from 1964 to 2020 (for oxidative DNA damage) and from 1907 to 2021 (for ROS) in Pubmed and Scopus databases were selected and analysed using Comprehensive Meta-Analysis version 2 respectively. Data were subjected to meta-analysis for examining the effect sizes of the results. Publication bias assessments, heterogeneity assessments and subgroup analyses based on biological specimens, patient status, illness duration and medication history were also conducted.
RESULTS: This meta-analysis revealed that oxidative DNA damage was significantly higher in patients with schizophrenia and bipolar disorder based on random-effects models whereas in depressed patients, the level was not significant. Since heterogeneity was present, results based on random-effects model was preferred. Our results also showed that oxidative DNA damage level was significantly higher in lymphocyte and urine of patients with schizophrenia and bipolar disorder respectively. Besides, larger effect size was observed in inpatients and those with longer illness duration and medication history. Significant higher ROS was also observed in schizophrenic patients but not in depressive patients.
CONCLUSION: The present meta-analysis found that oxidative DNA damage was significantly higher in schizophrenia and bipolar disorder but not in depression. The significant association between deoxyguanosines and mental illnesses suggested the possibility of using 8-OHdG or 8-oxodG as biomarker in measurement of oxidative DNA damage and oxidative stress. Higher ROS level indicated the involvement of oxidative stress in schizophrenia. The information from this study may provide better understanding on pathophysiology of mental illnesses.